相关论文: Probing LLMs for hate speech detection: strengths …

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

Given the black-box nature and complexity of large transformer language models (LM), concerns about generalizability and robustness present ethical implications for domains such as hate speech (HS) detection. Using the content rich Social…

Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. Although this method has proven to be effective for many domains, it might not always provide desirable…

The ubiquity of offensive and hateful content on online fora necessitates the need for automatic solutions that detect such content competently across target groups. In this paper we show that text classification models trained on large…

In this work, we designed unbiased prompts to systematically evaluate the psychological safety of large language models (LLMs). First, we tested five different LLMs by using two personality tests: Short Dark Triad (SD-3) and Big Five…

Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these *unverbalized biases*. Monitoring models via their stated reasoning is therefore…

The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

The prevalence of propaganda in our digital society poses a challenge to societal harmony and the dissemination of truth. Detecting propaganda through NLP in text is challenging due to subtle manipulation techniques and contextual…

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to…

There is a rapid increase in the use of multimedia content in current social media platforms. One of the highly popular forms of such multimedia content are memes. While memes have been primarily invented to promote funny and buoyant…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes it difficult for users to recognize biased predictions and…

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

For subjective tasks such as hate detection, where people perceive hate differently, the Large Language Model's (LLM) ability to represent diverse groups is unclear. By including additional context in prompts, we comprehensively analyze…

Warning: This paper contains examples of the language that some people may find offensive. Detecting and reducing hateful, abusive, offensive comments is a critical and challenging task on social media. Moreover, few studies aim to mitigate…

Online toxic language causes real harm, especially in regions with limited moderation tools. In this study, we evaluate how large language models handle toxic comments in Serbian, Croatian, and Bosnian, languages with limited labeled data.…

Academic researchers and social media entities grappling with the identification of hate speech face significant challenges, primarily due to the vast scale of data and the dynamic nature of hate speech. Given the ethical and practical…

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Social media influence campaigns pose significant challenges to public discourse and democracy. Traditional detection methods fall short due to the complexity and dynamic nature of social media. Addressing this, we propose a novel detection…